© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111083
    Prev
    Next
    INDEX
    Explanations

    "au revoir" and "bonjour"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ا
    1.73
    ו
    1.66
    و
    1.57
    اك
    1.45
    <0x0D>
    1.34
    다
    1.34
    는
    1.31
    at
    1.30
    ir
    1.29
    ா
    1.29
    POSITIVE LOGITS
    ties
    1.09
    ק
    1.04
    naire
    1.03
    st
    1.02
    тна
    1.02
    𝘨
    0.97
    سم
    0.96
     extraordinaire
    0.96
    src
    0.96
    structed
    0.94
    Activations Density 0.000%

    No Known Activations